01Safety
30.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 10%, unconfirmed writes 100%→100%.
Category breakdown
Where the score comes from.
Earned points across the four signals Gradable measures. Safety and Legibility are scored out of 30; Economics and Discoverability are scored out of 20.
02Legibility
29.5 / 30
03Economics
20.0 / 20
04Discoverability
13.0 / 20
Highest-impact fix
Estimated gain +7 pointsMake target tools discoverable on the first call
Clarify tool names, decision boundaries, and required argument schemas so an agent can choose and construct the target call without exploratory steps.
Description evidence
Defects and rewrites.
1 defect found across the exposed tool descriptions. Suggested rewrites make purpose, inputs, boundaries, and returns easier for an agent to understand.
| Tool | Defect types | Suggested rewrite |
|---|---|---|
fetch_page_content |
name_restates_behavior params_unexplained |
Fetches a web page and returns its content as markdown, optionally reduced to just the output of an extraction instruction. Use for reading a specific known URL (e.g. one found via search) rather than searching. Params: url — the page to fetch; max_chars — truncate returned content to this many characters (default 50000); live — if true, bypasses any cached/indexed copy and fetches the page fresh from the origin server (default false, which may return a cached version); prompt — optional natural-language instruction (e.g. "List all pricing tiers with their monthly prices") whose LLM-generated answer is returned instead of the full page content. |
Selection evidence
Confusable tool pairs.
0 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
| No confusable tool pairs were flagged in this assessment. | |||
Compare the field